Robot learning of everyday object manipulations via human demonstration

Abstract

Abstract-We deal with the problem of teaching a robot to manipulate everyday objects through human demonstration. We first design a task descriptor which encapsulates important elements of a task. The design originates from observations that manipulations involved in many everyday object tasks can be considered as a series of sequential rotations and translations, which we call manipulation primitives. We then propose a method that enables a robot to decompose a demonstrated task into sequential manipulation primitives and construct a task descriptor. We also show how to transfer a task descriptor learned from one object to similar objects. In the end, we argue that this framework is highly generic. Particularly, it can be used to construct a robot task database that serves as a manipulation knowledge base for a robot to succeed in manipulating everyday objects.

Recent Advances in Robot Learning from Demonstration

“…Several methods for automated segmentation of demonstrations into subtasks, based either on the similarity of component subtasks (136)(137)(138)(139)(140)(141) or on the occurrence of indicative events (25,142,143), have been explored.…”